mirror of
https://github.com/torvalds/linux.git
synced 2024-12-24 20:01:55 +00:00
b76ad88442
Currently dm-verity computes the hash of each block by using multiple
calls to the "ahash" crypto API. While the exact sequence depends on
the chosen dm-verity settings, in the vast majority of cases it is:
1. crypto_ahash_init()
2. crypto_ahash_update() [salt]
3. crypto_ahash_update() [data]
4. crypto_ahash_final()
This is inefficient for two main reasons:
- It makes multiple indirect calls, which is expensive on modern CPUs
especially when mitigations for CPU vulnerabilities are enabled.
Since the salt is the same across all blocks on a given dm-verity
device, a much more efficient sequence would be to do an import of the
pre-salted state, then a finup.
- It uses the ahash (asynchronous hash) API, despite the fact that
CPU-based hashing is almost always used in practice, and therefore it
experiences the overhead of the ahash-based wrapper for shash.
Because dm-verity was intentionally converted to ahash to support
off-CPU crypto accelerators, a full reversion to shash might not be
acceptable. Yet, we should still provide a fast path for shash with
the most common dm-verity settings.
Another reason for shash over ahash is that the upcoming multibuffer
hashing support, which is specific to CPU-based hashing, is much
better suited for shash than for ahash. Supporting it via ahash would
add significant complexity and overhead. And it's not possible for
the "same" code to properly support both multibuffer hashing and HW
accelerators at the same time anyway, given the different computation
models. Unfortunately there will always be code specific to each
model needed (for users who want to support both).
Therefore, this patch adds a new shash import+finup based fast path to
dm-verity. It is used automatically when appropriate. This makes
dm-verity optimized for what the vast majority of users want: CPU-based
hashing with the most common settings, while still retaining support for
rarer settings and off-CPU crypto accelerators.
In benchmarks with veritysetup's default parameters (SHA-256, 4K data
and hash block sizes, 32-byte salt), which also match the parameters
that Android currently uses, this patch improves block hashing
performance by about 15% on x86_64 using the SHA-NI instructions, or by
about 5% on arm64 using the ARMv8 SHA2 instructions. On x86_64 roughly
two-thirds of the improvement comes from the use of import and finup,
while the remaining third comes from the switch from ahash to shash.
Note that another benefit of using "import" to handle the salt is that
if the salt size is equal to the input size of the hash algorithm's
compression function, e.g. 64 bytes for SHA-256, then the performance is
exactly the same as no salt. This doesn't seem to be much better than
veritysetup's current default of 32-byte salts, due to the way SHA-256's
finalization padding works, but it should be marginally better.
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
135 lines
3.9 KiB
C
135 lines
3.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Copyright (C) 2012 Red Hat, Inc.
|
|
* Copyright (C) 2015 Google, Inc.
|
|
*
|
|
* Author: Mikulas Patocka <mpatocka@redhat.com>
|
|
*
|
|
* Based on Chromium dm-verity driver (C) 2011 The Chromium OS Authors
|
|
*/
|
|
|
|
#ifndef DM_VERITY_H
|
|
#define DM_VERITY_H
|
|
|
|
#include <linux/dm-io.h>
|
|
#include <linux/dm-bufio.h>
|
|
#include <linux/device-mapper.h>
|
|
#include <linux/interrupt.h>
|
|
#include <crypto/hash.h>
|
|
|
|
#define DM_VERITY_MAX_LEVELS 63
|
|
|
|
enum verity_mode {
|
|
DM_VERITY_MODE_EIO,
|
|
DM_VERITY_MODE_LOGGING,
|
|
DM_VERITY_MODE_RESTART,
|
|
DM_VERITY_MODE_PANIC
|
|
};
|
|
|
|
enum verity_block_type {
|
|
DM_VERITY_BLOCK_TYPE_DATA,
|
|
DM_VERITY_BLOCK_TYPE_METADATA
|
|
};
|
|
|
|
struct dm_verity_fec;
|
|
|
|
struct dm_verity {
|
|
struct dm_dev *data_dev;
|
|
struct dm_dev *hash_dev;
|
|
struct dm_target *ti;
|
|
struct dm_bufio_client *bufio;
|
|
char *alg_name;
|
|
struct crypto_ahash *ahash_tfm; /* either this or shash_tfm is set */
|
|
struct crypto_shash *shash_tfm; /* either this or ahash_tfm is set */
|
|
u8 *root_digest; /* digest of the root block */
|
|
u8 *salt; /* salt: its size is salt_size */
|
|
u8 *initial_hashstate; /* salted initial state, if shash_tfm is set */
|
|
u8 *zero_digest; /* digest for a zero block */
|
|
unsigned int salt_size;
|
|
sector_t data_start; /* data offset in 512-byte sectors */
|
|
sector_t hash_start; /* hash start in blocks */
|
|
sector_t data_blocks; /* the number of data blocks */
|
|
sector_t hash_blocks; /* the number of hash blocks */
|
|
unsigned char data_dev_block_bits; /* log2(data blocksize) */
|
|
unsigned char hash_dev_block_bits; /* log2(hash blocksize) */
|
|
unsigned char hash_per_block_bits; /* log2(hashes in hash block) */
|
|
unsigned char levels; /* the number of tree levels */
|
|
unsigned char version;
|
|
bool hash_failed:1; /* set if hash of any block failed */
|
|
bool use_bh_wq:1; /* try to verify in BH wq before normal work-queue */
|
|
unsigned int digest_size; /* digest size for the current hash algorithm */
|
|
unsigned int hash_reqsize; /* the size of temporary space for crypto */
|
|
enum verity_mode mode; /* mode for handling verification errors */
|
|
unsigned int corrupted_errs;/* Number of errors for corrupted blocks */
|
|
|
|
struct workqueue_struct *verify_wq;
|
|
|
|
/* starting blocks for each tree level. 0 is the lowest level. */
|
|
sector_t hash_level_block[DM_VERITY_MAX_LEVELS];
|
|
|
|
struct dm_verity_fec *fec; /* forward error correction */
|
|
unsigned long *validated_blocks; /* bitset blocks validated */
|
|
|
|
char *signature_key_desc; /* signature keyring reference */
|
|
|
|
struct dm_io_client *io;
|
|
mempool_t recheck_pool;
|
|
};
|
|
|
|
struct dm_verity_io {
|
|
struct dm_verity *v;
|
|
|
|
/* original value of bio->bi_end_io */
|
|
bio_end_io_t *orig_bi_end_io;
|
|
|
|
struct bvec_iter iter;
|
|
|
|
sector_t block;
|
|
unsigned int n_blocks;
|
|
bool in_bh;
|
|
|
|
struct work_struct work;
|
|
struct work_struct bh_work;
|
|
|
|
u8 real_digest[HASH_MAX_DIGESTSIZE];
|
|
u8 want_digest[HASH_MAX_DIGESTSIZE];
|
|
|
|
/*
|
|
* This struct is followed by a variable-sized hash request of size
|
|
* v->hash_reqsize, either a struct ahash_request or a struct shash_desc
|
|
* (depending on whether ahash_tfm or shash_tfm is being used). To
|
|
* access it, use verity_io_hash_req().
|
|
*/
|
|
};
|
|
|
|
static inline void *verity_io_hash_req(struct dm_verity *v,
|
|
struct dm_verity_io *io)
|
|
{
|
|
return io + 1;
|
|
}
|
|
|
|
static inline u8 *verity_io_real_digest(struct dm_verity *v,
|
|
struct dm_verity_io *io)
|
|
{
|
|
return io->real_digest;
|
|
}
|
|
|
|
static inline u8 *verity_io_want_digest(struct dm_verity *v,
|
|
struct dm_verity_io *io)
|
|
{
|
|
return io->want_digest;
|
|
}
|
|
|
|
extern int verity_hash(struct dm_verity *v, struct dm_verity_io *io,
|
|
const u8 *data, size_t len, u8 *digest, bool may_sleep);
|
|
|
|
extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
|
|
sector_t block, u8 *digest, bool *is_zero);
|
|
|
|
extern bool dm_is_verity_target(struct dm_target *ti);
|
|
extern int dm_verity_get_mode(struct dm_target *ti);
|
|
extern int dm_verity_get_root_digest(struct dm_target *ti, u8 **root_digest,
|
|
unsigned int *digest_size);
|
|
|
|
#endif /* DM_VERITY_H */
|